Summary of Transformer Neural Processes – Kernel Regression, by Daniel Jenson et al.
Transformer Neural Processes – Kernel Regression
by Daniel Jenson, Jhonathan Navott, Mengyan Zhang, Makkunda Sharma, Elizaveta Semenova, Seth Flaxman
First submitted to arxiv on: 19 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The Transformer Neural Process – Kernel Regression (TNP-KR) is a scalable neural process that rivals Gaussian Processes (GPs) in accuracy but still suffers from an O(n^2) bottleneck due to its attention mechanism. This paper introduces two novel attention mechanisms: scan attention (SA), which makes TNP-KR translation invariant, and deep kernel attention (DKA), which reduces complexity to O(n_c). These enhancements enable TNP-KR variants to perform inference with 100K context points on over 1M test points in under a minute. On various benchmarks, including meta regression, Bayesian optimization, image completion, and epidemiology, TNP-KR with DKA outperforms its Performer counterpart, while TNP-KR with SA achieves state-of-the-art results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper introduces a new neural process model called TNP-KR. It’s faster than the old models because it has two new ways to focus on important parts of the data: scan attention and deep kernel attention. These new methods make the model more accurate and efficient. The paper also shows that this new model works well on different kinds of tasks, like predicting things that happen in the future. |
Keywords
» Artificial intelligence » Attention » Inference » Optimization » Regression » Transformer » Translation
